One of the more interesting dynamics of the past eight-or-so years has been watching a bunch of the people who [taught me my values] and [served as my early role models] and [were presented to me as paragons of cultural virtue] going off the deep end.
I’m curious who these people are.
We should expect regression towards the mean only if the tasks were selected for having high “improvement from small to Gopher-7”. Were they?
The reasoning was given in the comment prior to it, that we want fast progress in order to get to immortality sooner.
“But yeah, I wish this hadn’t happened.”
Who else is gonna write the article? My sense is that no one (including me) is starkly stating publically the seriousness of the situation.
“Yudkowsky is obnoxious, arrogant, and most importantly, disliked, so the more he intertwines himself with the idea of AI x-risk in the public imagination, the less likely it is that the public will take those ideas seriously”
I’m worried about people making character attacks on Yudkowsky (or other alignment researchers) like this. I think the people who think they can probably solve alignment by just going full-speed ahead and winging it, they are arrogant. Yudkowsky’s arrogant-sounding comments about how we need to be very careful and slow, are negligible in comparison. I’m guessing you agree with this (not sure) and we should be able to criticise him for his communication style, but I am a little worried about people publically undermining Yudkowsky’s reputation in that context. This seems like not what we would do if we were trying to coordinate well.
“We finally managed to solve the problem of deceptive alignment while being capabilities competitive”
??????
“But I don’t think you even need Eliezer-levels-of-P(doom) to think the situation warrants that sort of treatment.”
Agreed. If a new state develops nuclear weapons, this isn’t even close to creating a 10% x-risk, yet the idea of airstrikes on nuclear enrichment facillities, even though it is very controversial, has for a long time very much been an option on the table.
“if I thought the chance of doom was 1% I’d say “full speed ahead!”
This is not a reasonable view. Not on Longtermism, nor on mainstream common sense ethics. This is the view of someone willing to take unacceptable risks for the whole of humanity.
Also, there is a big difference between “Calling for violence”, and “calling for the establishment of an international treaty, which is to be enforced by violence if necessary”. I don’t understand why so many people are muddling this distinction.
You are muddling the meaning of “pre-emptive war”, or even “war”. I’m not trying to diminish the gravity of Yudkowsky’s proposal, but a missile strike on a specific compound known to contain WMD-developing technology is not a “pre-emptive war” or “war”. Again I’m not trying to diminish the gravity, but this seems like an incorrect use of the term.
“For instance, personally I think the reason so few people take AI alignment seriously is that we haven’t actually seen anything all that scary yet. “
And if this “actually scary” thing happens, people will know that Yudkowsky wrote the article beforehand, and they will know who the people are that mocked it.
I agree. Though is it just the limited context window that causes the effect? I may be mistaken, but from my memory it seems like they emerge sooner than you would expect if this was the only reason (given the size of the context window of gpt3).
Therefore, the waluigi eigen-simulacra are attractor states of the LLM
It seems to me like this informal argument is a bit suspect. Actually I think this argument would not apply to Solomonof Induction.
Suppose we have to programs that have distributions over bitstrings. Suppose p1 assigns uniform probability to each bitstring, while p2 assigns 100% probability to the string of all zeroes. (equivalently, p1 i.i.d. samples bernoully from {0,1}, p2 samples 0 i.i.d. with 100%).
Suppose we use a perfect Bayesian reasoner to sample bitstrings, but we do it in precisely the same way LLMs do it according to the simulator model. That is, given a bitstring, we first formulate a posterior over programs, i.e. a “superposition” on programs, which we use to sample the next bit, then we recompute the posterior, etc.
Then I think the probability of sampling 00000000… is just 50%. I.e. I think the distribution over bitstrings that you end up with is just the same as if you just first sampled the program and stuck with it.
I think tHere’s a messy calculation which could be simplified (which I won’t do):
Limit of this is 0.5.
I don’t wanna try to generalize this, but based on this example it seems like if an LLM was an actual Bayesian, Waluigi’s would not be attractors. The informal argument is wrong because it doesn’t take into account the fact that over time you sample increasingly many non-waluigi samples, pushing down the probability of Waluigi.
Then again, the presense of a context window completely breaks the above calculation in a way that preserves the point. Maybe the context window is what makes Waluigi’s into an attractor? (Seems unlikely actually, given that the context windows are fairly big).
Linking to my post about Dutch TV: https://www.lesswrong.com/posts/TMXEDZy2FNr5neP4L/datapoint-median-10-ai-x-risk-mentioned-on-dutch-public-tv
“When LessWrong was ~dead”
Which year are you referring to here?
A lot of people in AI Alignment I’ve talked to have found it pretty hard to have clear thoughts in the current social environment, and many of them have reported that getting out of Berkeley, or getting social distance from the core of the community has made them produce better thoughts.
What do you think is the mechanism behind this?
There is a general phenomenon where:
Person A has mental model X and tries to explain X with explanation Q
Person B doesn’t get model X from Q, thinks a bit, and then writes explanation P, reads P and thinks: P is how it should have been explained all along, and Q didn’t actually contain the insights, but P does.
Person C doesn’t get model X from P, thinks a bit, and then writes explanation R, reads R and thinks: …
It seems to me quite likely that you are person B, thinking they explained something because THEY think their explanation is very good and contains all the insights that the previous ones didn’t. Some of the evidence for this is in fact contained in your very comment:
“1. Pointing out the “reward chisels computation” point. 2. Having some people tell me it’s obvious, or already known, or that they already invented it. 3. Seeing some of the same people continue making similar mistakes (according to me)”
So point 3 basically almost definitively proves that your mental model is not conveyed to those people in your post, does it not? I think a similar thing happened where that mental model was not conveyed to you from RFLO, even though we tried to convey it. (btw not saying the models that RFLO tried to explain are the same as this post, but the basic idea of this post definitely is a part of RFLO).
BTW, it could in fact be that person B’s explanation is clearer. (otoh, I think some things are less clear, e.g. you talk about “the” optimization target, which I would say is referring to that of the mesa-optimizer, without clearly assuming there is a mesa-optimizer. We stated the terms mesa- and base-optimizer to clearly make the distinction. There are a bunch of other things that I think are just imprecise, but let’s not get into it).
“Continuing (AFAICT) to correct people on (what I claim to be) mistakes around reward and optimization targets, and (for a while) was ~the only one doing so.”
I have been correcting people for a while on stuff like that (though not on LW, I’m not often on LW), such as that in the generic case we shouldn’t expect wireheading from RL agents unless the option of wireheading is in the training environment, for basically these reasons. I would also have expected people to just get this after reading RFLO, but many didn’t (others did), so your points 1/2/3 also apply to me.
“I do totally buy that you all had good implicit models of the reward-chiseling point”. I don’t think we just “implicitly” modeled it, we very explicitly understood it and it ran throughout our whole thinking about the topic. Again, explaining stuff is hard though, I’m not claiming we conveyed everything well to everyone (clearly you haven’t either).
Very late reply, sorry.
“even though reward is not a kind of objective”, this is a terminological issue. In my view, calling a “antecedent-computation reinforcement criterion” an “objective” matches my definition of “objective”, and this is just a matter of terminology. The term “objective” is ill-defined enough that “even though reward is not a kind of objective” is a terminological claim about objective, not a claim about math/the world.
The idea that RL agents “reinforce antecedent computations” is completely core to our story of deception. You could not make sense of our argument for deception if you didn’t look at RL systems in this way. Viewing the base optimizer as “trying” to achieve an “objective” but “failing” because it is being “deceived” by the mesa optimizer is purely a metaphorical/terminological choice. It doesn’t negate the fact that we all understood that the base optimizer is just reinforcing “antecedent computations”. How else could you make sense of the story of deception, where an existing model, which represents the mesa optimizer, is being reinforced by the base optimizer because that existing model understands the base optimizer’s optimization process?
I am not claiming that the RFLO communicated this point well, just that it was understood and absolutely was core to the paper, and large parts of the paper wouldn’t even make sense if you didn’t have this insight. (Certainly the fact that we called it an objective doesn’t communicate the point, and it isn’t meant to).
Could you edit this comment to add which three books you’re referring to?